Zhizhuo Kou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhizhuo Kou has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Sirui Han
The Hong Kong University of Science and Technology, Hong Kong, China
6 shared publications - Yike Guo
Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, China
6 shared publications - Yuyao Zhang
HKUST, Hong Kong
3 shared publications - Haoran Li
HKUST, Hong Kong
2 shared publications - Yakun Cui
HKUST, Hong Kong
2 shared publications - Yanting Zhang
HKUST, Hong Kong
2 shared publications
Latest Publications
- Open Access
- 22 May 2026
- Published by Emerald Publishing in China Accounting and Finance Review
- Vol. 28 (4) , 1-26
Artificial intelligence in financial markets: a literature review and research agenda
Purpose: This paper is targeted at researchers in the fields of economics and finance and presents a comprehensive literature review of artificial intelligence (AI) applications in finance, examining research published in leading finance and economics journals. Our analysis reveals significant advances in algorithmic trading, credit scoring, fraud detection and regulatory compliance while highlighting persistent challenges in model interpretability, fairness and systemic risk. Design/methodology/approach: Our analysis encompasses 138 carefully selected papers published between January 2019 and December 2024, with an initial analysis of pre-prints and early 2025 publications to capture the latest trends. This study employs a structured literature review methodology, systematically searching top-tier finance and economics journals, including UTD24 Journals, FT50 Journals and additional leading publications in finance and economics. To maintain a clear economic perspective, we explicitly exclude purely technical computer science literature, focusing instead on papers that contribute to our understanding of AI's economic implications for financial markets. Findings: Our synthesis reveals AI's dual impact that while models like advanced machine learning methods enhance predictive accuracy in asset pricing and expand credit access, they also introduce challenges in interpretability, algorithmic fairness and new vectors for systemic risk, such as algorithmic collusion. In China's unique regulatory environment, characterized by strict algorithmic disclosure requirements and quantitative trading thresholds, these challenges are particularly acute as regulators balance innovation with market stability concerns. Further research and policy development are needed to ensure AI's responsible integration into financial systems. Originality/value: This paper provides a comprehensive review of AI in finance from an economic theory perspective, examining fundamental questions like algorithmic collusion, Nash equilibria among AI agents and cross-border data regulation. It offers a structured intellectual map and forward-looking research agenda with relevance for both developed and emerging markets.
- 22 May 2026
- Published by Emerald Publishing in China Accounting and Finance Review
- Vol. 28 (4) , 1-26
Open AccessArtificial intelligence in financial markets: a literature review and research agenda
Purpose: This paper is targeted at researchers in the fields of economics and finance and presents a comprehensive literature review of artificial intelligence (AI) applications in finance, examining research published in leading finance and economics journals. Our analysis reveals significant advances in algorithmic trading, credit scoring, fraud detection and regulatory compliance while highlighting persistent challenges in model interpretability, fairness and systemic risk. Design/methodology/approach: Our analysis encompasses 138 carefully selected papers published between January 2019 and December 2024, with an initial analysis of pre-prints and early 2025 publications to capture the latest trends. This study employs a structured literature review methodology, systematically searching top-tier finance and economics journals, including UTD24 Journals, FT50 Journals and additional leading publications in finance and economics. To maintain a clear economic perspective, we explicitly exclude purely technical computer science literature, focusing instead on papers that contribute to our understanding of AI's economic implications for financial markets. Findings: Our synthesis reveals AI's dual impact that while models like advanced machine learning methods enhance predictive accuracy in asset pricing and expand credit access, they also introduce challenges in interpretability, algorithmic fairness and new vectors for systemic risk, such as algorithmic collusion. In China's unique regulatory environment, characterized by strict algorithmic disclosure requirements and quantitative trading thresholds, these challenges are particularly acute as regulators balance innovation with market stability concerns. Further research and policy development are needed to ensure AI's responsible integration into financial systems. Originality/value: This paper provides a comprehensive review of AI in finance from an economic theory perspective, examining fundamental questions like algorithmic collusion, Nash equilibria among AI agents and cross-border data regulation. It offers a structured intellectual map and forward-looking research agenda with relevance for both developed and emerging markets.
- Open Access
- 9 May 2026
- Published by MDPI AG in Preprints.org
Learning to Fuse: Cost-Sensitive Credit Assessment via Hierarchical Multi-Agent Reinforcement Learning
Credit risk assessment requires both accurate prediction and structured decomposition of how hetero-geneous evidence contributes to each decision. Monolithic Large Language Models can incorporate unstructured evidence and natural-language reasoning into such workflows, but in high-stakes un- derwriting they may be distracted by noisy inputs, miss rare but decisive risk cues, and offer limited control over policy-dependent decision thresholds. We present CREDITAGENT, a hierarchical credit review system with three stages: evidence filtering, specialist risk analysis by agents, and decision fusion. Our central contribution is holding the adapted backbone, specialist-agent outputs, hard-stop rules, and data split fixed, we vary only the final fusion strategy to isolate the effect of hierarchical fusion on underwriting quality. On a held-out set of 6,000 personal credit cases from Chinese financial institution, CREDITAGENT achieves 83.32% accuracy and a Business Efficiency Coefficient of 0.7647 outperform flagship model. We present these findings as an institution-specific case study while identifying which components (hierarchical fusion, GRPO training recipe) are mechanism-portable versus institution-specific (hard-stop rules, cost ratios). To ensure reproducibility, we make code and dataset publicly available at https://github.com/kouzhizhuo/Credit_Agents.
- 9 May 2026
- Published by MDPI AG in Preprints.org
Open AccessLearning to Fuse: Cost-Sensitive Credit Assessment via Hierarchical Multi-Agent Reinforcement Learning
Credit risk assessment requires both accurate prediction and structured decomposition of how hetero-geneous evidence contributes to each decision. Monolithic Large Language Models can incorporate unstructured evidence and natural-language reasoning into such workflows, but in high-stakes un- derwriting they may be distracted by noisy inputs, miss rare but decisive risk cues, and offer limited control over policy-dependent decision thresholds. We present CREDITAGENT, a hierarchical credit review system with three stages: evidence filtering, specialist risk analysis by agents, and decision fusion. Our central contribution is holding the adapted backbone, specialist-agent outputs, hard-stop rules, and data split fixed, we vary only the final fusion strategy to isolate the effect of hierarchical fusion on underwriting quality. On a held-out set of 6,000 personal credit cases from Chinese financial institution, CREDITAGENT achieves 83.32% accuracy and a Business Efficiency Coefficient of 0.7647 outperform flagship model. We present these findings as an institution-specific case study while identifying which components (hierarchical fusion, GRPO training recipe) are mechanism-portable versus institution-specific (hard-stop rules, cost ratios). To ensure reproducibility, we make code and dataset publicly available at https://github.com/kouzhizhuo/Credit_Agents.
- Open Access
- 8 May 2026
- Published by MDPI AG in Preprints.org
When to Route? Regime-Adaptive Meta-Policies for Hierarchical Portfolio Agents
Modular decision systems expose multiple operating points, but downstream utility can vary by regime. Portfolio construction is a useful setting because routing, aggregation, and allocation can help or hurt depending on market structure. We instantiate a hierarchy with three operating points: direct optimizer, routed consensus, and alpha-augmented optimizer. Across universes, these modes are not uniformly ranked. Routing helps when dispersion/decorrelation is high; direct optimization is safer in low-signal settings; alpha augmentation helps in concentrated signal-rich settings. We identify the market characteristics (cross-sectional dispersion, concentration, forecast signal density) that predict which mode dominates. A rolling adaptive meta-policy that selects among operating points based on recent performance achieves competitive or superior risk-return profiles without foreknowledge of the optimal mode. We validate against classical baselines demonstrate that the operating-point structure persists across time frequencies from 15-minute bars to daily rebalancing, and confirm robustness under realistic transaction costs (0--15 bps). More broadly, our results suggest for hierarchical decision systems: the key is not to find one universally best configuration, but to characterize when each operating mode is most effective. To support future research and ensure reproducibility, we make source code publicly available at https://github.com/kouzhizhuo/Regime-Adaptive-Portfolio-Agents.
- 8 May 2026
- Published by MDPI AG in Preprints.org
Open AccessWhen to Route? Regime-Adaptive Meta-Policies for Hierarchical Portfolio Agents
Modular decision systems expose multiple operating points, but downstream utility can vary by regime. Portfolio construction is a useful setting because routing, aggregation, and allocation can help or hurt depending on market structure. We instantiate a hierarchy with three operating points: direct optimizer, routed consensus, and alpha-augmented optimizer. Across universes, these modes are not uniformly ranked. Routing helps when dispersion/decorrelation is high; direct optimization is safer in low-signal settings; alpha augmentation helps in concentrated signal-rich settings. We identify the market characteristics (cross-sectional dispersion, concentration, forecast signal density) that predict which mode dominates. A rolling adaptive meta-policy that selects among operating points based on recent performance achieves competitive or superior risk-return profiles without foreknowledge of the optimal mode. We validate against classical baselines demonstrate that the operating-point structure persists across time frequencies from 15-minute bars to daily rebalancing, and confirm robustness under realistic transaction costs (0--15 bps). More broadly, our results suggest for hierarchical decision systems: the key is not to find one universally best configuration, but to characterize when each operating mode is most effective. To support future research and ensure reproducibility, we make source code publicly available at https://github.com/kouzhizhuo/Regime-Adaptive-Portfolio-Agents.
- Open Access
- 21 April 2026
- Published by MDPI AG in Preprints.org
CCLUPE: Benchmark for Credit Context Log Understanding and Prediction Evaluation
While Large Language Models (LLMs) have shown great promise in transforming credit risk assess-ment, existing evaluation frameworks are almost exclusively concerned with general financial NLP tasks and neglect the specific reasoning needed by practitioners. To address this, we develop the Credit Context Log Understanding and Prediction Evaluation (CCLUPE) benchmark. Unlike the previous benchmarks, CCLUPE aims to capture and evaluate the intricate reasoning unique to each constituent of the Chinese credit market, where evaluations are heavily based on the integration and synthesis of complex transacted logs and the prediction of hidden financial behaviors. Unlike previous benchmarks, CCLUPE aims to capture and evaluate the intricate reasoning unique to each constituent of the Chinese credit market. Unlike previous benchmarks, CCLUPE aims to capture and evaluate the intricate reasoning unique to each constituent. CCLUPE boasts more than 4,000 premium samples segmented by individual and micro-enterprise customers and distributed among 7 principal log types and 16 sub log types. A comprehensive assessment process involving upwards of 20 professional annotators is enacted to guarantee the quality of the dataset. Moreover, we introduce Log-Score, a novel evaluation metric designed to incorporate log misunderstanding penalties and assess multifaceted competencies. Even the state-of-the-art models underperform when it comes to these high-stakes tasks. CCLUPE serves as a rigorous testbed for the next generation of financial LLMs, ensuring their robustness for deployment in complex real credit scenarios.
- 21 April 2026
- Published by MDPI AG in Preprints.org
Open AccessCCLUPE: Benchmark for Credit Context Log Understanding and Prediction Evaluation
While Large Language Models (LLMs) have shown great promise in transforming credit risk assess-ment, existing evaluation frameworks are almost exclusively concerned with general financial NLP tasks and neglect the specific reasoning needed by practitioners. To address this, we develop the Credit Context Log Understanding and Prediction Evaluation (CCLUPE) benchmark. Unlike the previous benchmarks, CCLUPE aims to capture and evaluate the intricate reasoning unique to each constituent of the Chinese credit market, where evaluations are heavily based on the integration and synthesis of complex transacted logs and the prediction of hidden financial behaviors. Unlike previous benchmarks, CCLUPE aims to capture and evaluate the intricate reasoning unique to each constituent of the Chinese credit market. Unlike previous benchmarks, CCLUPE aims to capture and evaluate the intricate reasoning unique to each constituent. CCLUPE boasts more than 4,000 premium samples segmented by individual and micro-enterprise customers and distributed among 7 principal log types and 16 sub log types. A comprehensive assessment process involving upwards of 20 professional annotators is enacted to guarantee the quality of the dataset. Moreover, we introduce Log-Score, a novel evaluation metric designed to incorporate log misunderstanding penalties and assess multifaceted competencies. Even the state-of-the-art models underperform when it comes to these high-stakes tasks. CCLUPE serves as a rigorous testbed for the next generation of financial LLMs, ensuring their robustness for deployment in complex real credit scenarios.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-22
CareerCraft: Supporting New Graduates on Job Hunting with LLM-Assisted Self-Construction of Career Profile
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Open AccessCareerCraft: Supporting New Graduates on Job Hunting with LLM-Assisted Self-Construction of Career Profile
- Open Access
- 12 February 2026
- Published by MDPI AG in Preprints.org
Trustworthy Legal Reasoning: A Comprehensive Survey
As large language models are increasingly used for contract drafting, case research and even judicial work, a central question is how to make their outputs trustworthy. This survey addresses that question through the lens of verified generation for legal AI, focusing on systems that are robust against hallucinations and traceable to authoritative legal sources. First, we propose a unified framework for verified generation in legal AI, linking reasoning, retrieval, and validation around factual reliability. Second, we cast reliability methods into two paradigms of epistemic negotiation, by failure and by conflict, enabling models to recognize and act on their competence limits. Third, we survey the legal-AI landscape and identify challenges for verifiable, governance-native systems. This survey outlines a roadmap for trustworthy legal AI and for reliable reasoning beyond the legal domain.
- 12 February 2026
- Published by MDPI AG in Preprints.org
Open AccessTrustworthy Legal Reasoning: A Comprehensive Survey
As large language models are increasingly used for contract drafting, case research and even judicial work, a central question is how to make their outputs trustworthy. This survey addresses that question through the lens of verified generation for legal AI, focusing on systems that are robust against hallucinations and traceable to authoritative legal sources. First, we propose a unified framework for verified generation in legal AI, linking reasoning, retrieval, and validation around factual reliability. Second, we cast reliability methods into two paradigms of epistemic negotiation, by failure and by conflict, enabling models to recognize and act on their competence limits. Third, we survey the legal-AI landscape and identify challenges for verifiable, governance-native systems. This survey outlines a roadmap for trustworthy legal AI and for reliable reasoning beyond the legal domain.
- Top Cited PapersOpen Access
- 3 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (7) , 1-37
Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey
Predicting stock prices presents a challenging research problem due to the inherent volatility and non-linear nature of the stock market. In recent years, knowledge-enhanced stock price prediction methods have shown groundbreaking results by utilizing external knowledge to understand the stock market. Despite the importance of these methods, there is a scarcity of scholarly works that systematically synthesize previous studies from the perspective of external knowledge types. Specifically, the external knowledge can be modeled in different data structures, which we group into non-graph-based formats and graph-based formats: (1) non-graph-based knowledge captures contextual information and multimedia descriptions specifically associated with an individual stock; (2) graph-based knowledge captures interconnected and interdependent information in the stock market. This survey article aims to provide a systematic and comprehensive description of methods for acquiring external knowledge from various unstructured data sources and then incorporating it into stock price prediction models. We also explore fusion methods for combining external knowledge with historical price features. Moreover, this article includes a compilation of relevant datasets and delves into potential future research directions in this domain.
- 3 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (7) , 1-37
Top Cited PapersOpen AccessMethods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey
Predicting stock prices presents a challenging research problem due to the inherent volatility and non-linear nature of the stock market. In recent years, knowledge-enhanced stock price prediction methods have shown groundbreaking results by utilizing external knowledge to understand the stock market. Despite the importance of these methods, there is a scarcity of scholarly works that systematically synthesize previous studies from the perspective of external knowledge types. Specifically, the external knowledge can be modeled in different data structures, which we group into non-graph-based formats and graph-based formats: (1) non-graph-based knowledge captures contextual information and multimedia descriptions specifically associated with an individual stock; (2) graph-based knowledge captures interconnected and interdependent information in the stock market. This survey article aims to provide a systematic and comprehensive description of methods for acquiring external knowledge from various unstructured data sources and then incorporating it into stock price prediction models. We also explore fusion methods for combining external knowledge with historical price features. Moreover, this article includes a compilation of relevant datasets and delves into potential future research directions in this domain.
- Top Cited PapersOpen Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18517-18533
Automate Strategy Finding with LLM in Quant Investment
Zhizhuo Kou, Holam Yu, Junyu Luo, Jingshu Peng, Xujia Li, Chengzhong Liu, Juntao Dai, Lei Chen, Sirui Han, Yike Guo. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18517-18533
Top Cited PapersOpen AccessAutomate Strategy Finding with LLM in Quant Investment
Zhizhuo Kou, Holam Yu, Junyu Luo, Jingshu Peng, Xujia Li, Chengzhong Liu, Juntao Dai, Lei Chen, Sirui Han, Yike Guo. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.